Commit Graph

1534 Commits

Author SHA1 Message Date
Yichen Jiang
ece8645080 fix: suppress runtime context in minimal profiles 2026-08-12 23:28:15 +08:00
xjt
4806d94715 docs(i18n): include complete proofreading corpus 2026-08-12 12:30:19 +08:00
xjt
7b450d121e docs(i18n): apply reviewed Chinese proofreading updates 2026-08-12 09:59:19 +08:00
Yichen Jiang
0a0737f33b Merge pull request #1873 from deepseek-harness/fix/code-mode-executor-collapse
fix(tools): collapse code-mode executor to run_code for model-direct calls
2026-08-11 23:22:54 +08:00
Yichen Jiang
e258cf7a2d fix(tools): resolve the collapse through the scope, not the deployment default
`collapses()` read `defaultMode`, so the collapse only applied when the
DEPLOYMENT was `code`. An agent handed `code` by an agent preset under a
native default announced `[run_code]` on the wire and still executed a
model-direct native call -- the bypass this collapse exists to close,
reopened for exactly the composition `dsh-agent-tool-mode` produces.

`modeFor(scope)` is the same resolution `wireSchemas` and the SDK section
already use, so presentation and execution cannot disagree, and a mode
inherited from a standing preset scope collapses like a declared one.

The per-agent and preset tests asserted only the wire, which is why the
regression passed them. They now assert through the executor: the body
never runs, the call resolves UNKNOWN_TOOL, and the native sibling beside
it still executes.
2026-08-11 22:53:17 +08:00
imccyu
5ca7be5dcb release(dsh): 0.0.1-rc.2 2026-08-11 22:52:39 +08:00
Yichen Jiang
5d2c943d38 fix(tools): state the code-mode collapse in the prompt and the denial
The executor collapse landed without telling the model it exists. Every
tool contributes its own guidance section naming its tool, none of them
qualify how that tool is reached, and they all render before the SDK
(orders 100-199 against SDK_SECTION_ORDER 150), so the prompt said "Use
the read tool" eleven times and never said only run_code is callable.

A real session shows the consequence: the model emitted a native call,
read `unknown tool "read"` for a tool the same prompt declares, and
concluded the deployment was inconsistent rather than routing through
run_code.

The registry now contributes `tools:code-only` at order 99 -- ahead of
the guidance band -- stating the rule, registered wherever `tools:sdk`
is and rendering empty outside an effective `code`. `both` renders it
empty because its native calls do execute, which is also why
both-mode-turn no longer shares code-mode-turn's expected prompt. The
denial itself now names the route back, since a bare UNKNOWN_TOOL for a
declared tool is what misled the model.
2026-08-11 22:51:16 +08:00
Chinesezjc
47f108bf50 test(tools): use type-safe error assertions instead of any casts
oxlint's no-unsafe-member-access rejects member access through an any
cast; the error info is reachable through the declared optional chain.
2026-08-11 22:40:36 +08:00
Chinesezjc
610dc74ea8 test(tools): fix error code assertions for collapsed call tests
The error code lives on ToolFailure.info.code, not ToolFailure.code.
2026-08-11 22:40:36 +08:00
Chinesezjc
6d0a7c12e1 test(tools): add coverage for collapsed model-direct call under code mode
Add two executor-level tests covering the previously uncovered branches
in createExecution:
- collapsed call (non-aborted signal) returns UNKNOWN_TOOL
- collapsed call (pre-aborted signal) returns ABORTED_BEFORE_DISPATCH
2026-08-11 22:40:36 +08:00
Chinesezjc
1e78513806 fix(tools): add collapses() method and fix createExecution collapse logic 2026-08-11 22:40:36 +08:00
Chinesezjc
24dd48b133 fix(tools): collapse code-mode executor to run_code for model-direct calls
wireSchemas() already advertised only run_code under mode: 'code', but the
executor resolved every call through get(), which returns the full visible
map plus the reserved transport. A model could name a native tool directly
and bypass run_code entirely. Route the execution-path lookups through a
new private resolveExecution() that applies the mode collapse at the
operation boundary: model-direct calls under 'code' may only name run_code
(UNKNOWN_TOOL otherwise), while SDK sub-dispatches (parent token set) keep
every visible tool. get()/schemas() public semantics are unchanged.

The denial happens at createExecution, before the extensible policy
pipeline — pre-execute listeners, approval ask, and guards never observe
a call that is deterministically denied. A collapsed call honors the
pre-dispatch cancellation contract, routes aborted results through the
visible tool's finalizeContent, and captures the finalizer before
argument materialization.

Regenerated docs, catalogs, graphs, scoped events, re-recorded
translation pairs, and updated test assertions.

Fixes #1815
2026-08-11 22:40:36 +08:00
Chinesezjc
2aef2d83fa fix(tools): remove tool:* prompt filtering per review feedback
LegGasai noted that filtering prompt sections by tool:* prefix is a poor
heuristic: it conflates section naming convention with presentation
semantics and would incorrectly drop tool:structured_output. The executor
collapse already enforces the boundary — a model-direct native call is
rejected as UNKNOWN_TOOL regardless of what the prompt says, so filtering
the prompt adds no security and only risks losing useful guidance.

The tool:read/tool:bash/etc sections describe capability usage patterns
that apply to both native and code presentations, and keeping them does
not reopen the native direct-call path because the executor blocks it.
2026-08-11 22:40:36 +08:00
Chinesezjc
b558afc373 fix(tools): use @deepseek-ai/cordis import in README type blocks 2026-08-11 22:40:20 +08:00
Chinesezjc
6f6defd64a fix(tools): collapse code-mode executor to run_code for model-direct calls
wireSchemas() already advertised only run_code under mode: 'code', but the
executor resolved every call through get(), which returns the full visible
map plus the reserved transport. A model could name a native tool directly
and bypass run_code entirely. Route the execution-path lookups through a
new private resolveExecution() that applies the mode collapse at the
operation boundary: model-direct calls under 'code' may only name run_code
(UNKNOWN_TOOL otherwise), while SDK sub-dispatches (parent token set) keep
every visible tool. get()/schemas() public semantics are unchanged.

The denial happens at createExecution, before the extensible policy
pipeline — pre-execute listeners, approval ask, and guards never observe
a call that is deterministically denied. A collapsed call honors the
pre-dispatch cancellation contract, routes aborted results through the
visible tool's finalizeContent, and captures the finalizer before
argument materialization.

Under code mode, a system-prompt/assemble listener filters out tool:*
guidance sections that told the model to call native tools directly.
The tools:sdk section and SDK types remain so programs can still use
all tools through run_code.

Regenerated docs, catalogs, graphs, scoped events, and re-recorded
translation pairs.

Fixes #1815
2026-08-11 22:40:20 +08:00
Chinesezjc
75a09efd51 fix(tools): use @deepseek-ai/cordis and @deepseek-ai/schemastery imports 2026-08-11 22:40:19 +08:00
Chinesezjc
4806fdabab fix(tools): collapse code-mode executor to run_code for model-direct calls
wireSchemas() already advertised only run_code under mode: 'code', but the
executor resolved every call through get(), which returns the full visible
map plus the reserved transport. A model could name a native tool directly
and bypass run_code entirely. Route the execution-path lookups through a
new private resolveExecution() that applies the mode collapse at the
operation boundary: model-direct calls under 'code' may only name run_code
(UNKNOWN_TOOL otherwise), while SDK sub-dispatches (parent token set) keep
every visible tool. get()/schemas() public semantics are unchanged.

The denial happens at createExecution, before the extensible policy
pipeline — pre-execute listeners, approval ask, and guards never observe
a call that is deterministically denied. A collapsed call honors the
pre-dispatch cancellation contract, routes aborted results through the
visible tool's finalizeContent, and captures the finalizer before
argument materialization.

Under code mode, a system-prompt/assemble listener filters out tool:*
guidance sections that told the model to call native tools directly.
The tools:sdk section and SDK types remain so programs can still use
all tools through run_code.

Fixes #1815
2026-08-11 22:40:19 +08:00
Tianyi Cui
9dc4af386d Merge branch 'master' into worktree/schedule-conversational-after 2026-08-11 20:31:49 +08:00
Tianyi Cui
5f64b6815c Merge remote-tracking branch 'origin/master' into worktree/schedule-conversational-after
# Conflicts:
#	docs/event-producer-consumer.i18n.yaml
#	docs/event-producer-consumer.md
#	docs/event-producer-consumer.zh.md
2026-08-11 19:54:39 +08:00
Yichen Jiang
fb6fb1fa12 Merge origin/master into worktree/web-plugin-config, adapting to ctx.remote.$on
#2201 landed three moves this branch sits on top of. `bindSettingsScope` became
`ctx.settingsScope.bind` on the Settings surface, so the section injects that
service and the Remote face instead of importing a free function; the
`SettingsScope` types moved into the runtime contract module, which is where
this branch's `base`, `user`, and `unset` now live; and the client
`credentials/changed` event became the forwarded owner event
`credentials/updated`, which the web-search card subscribes to through
`ctx.remote.$on`.

The generated module graph crossed mermaid's 1000-edge render guard with this
branch's 14 new edges. The guard doubles again, exactly as it did at 500 — the
graph counts real package edges, and trimming them to fit a renderer default
would make the document lie about the dependency set.
2026-08-11 19:52:34 +08:00
imccyu
d88f771e19 feat(remote): deliver allowlisted Host events through ctx.remote.$on
api/remotes owns the allowlist and its type projection; type-meta owns the shape
predicate, the selection seat, and the internal remote/host-event carrier
signal; api/gateway's Client half turns that signal into $on callbacks through a
private dispatch. apiproxy forwards each allowlisted emission verbatim in one
host/remote-event frame, registered ahead of the derived invalidation frames so
frame order is unchanged, and drops the three per-event variants it replaces.
Owner packages move their Events declarations into client-safe ./types exports,
so a consumer's listener signature is the Host's own declaration.
2026-08-11 19:25:40 +08:00
Tianyi Cui
32a9a0ac61 Merge remote-tracking branch 'origin/master' into worktree/schedule-conversational-after 2026-08-11 19:10:26 +08:00
Tianyi Cui
3f01ff8291 Merge remote-tracking branch 'origin/master' into worktree/schedule-conversational-after 2026-08-11 19:05:13 +08:00
Yichen Jiang
8efb2bc9a2 Merge origin/master into worktree/web-plugin-config
Three seams: the tsconfig path map gained a mapping on each side and keeps
both; the event-producer matrix is generated, so it was regenerated rather
than hand-merged row by row.
2026-08-11 18:27:53 +08:00
pku-xht
b38e02462b Merge commit '5427cbcc19cfd1ce9f3af1ae22207852cc5740fa' into codex/workflow-runs-chat-node-f6 2026-08-11 18:09:43 +08:00
Turtle
096586886a fix(review): address terminology feedback 2026-08-11 15:23:05 +08:00
Turtle
0c708cb10d refactor: replace overloaded surface terminology 2026-08-11 15:23:05 +08:00
Hypatia May
ef8637f864 Merge branch 'feat/subagent-report-semantics' into feat/subagent-settlement-delivery
# Conflicts:
#	docs/event-producer-consumer.i18n.yaml
#	docs/event-producer-consumer.md
2026-08-11 14:52:49 +08:00
Hypatia May
9340604ea5 Merge branch 'feat/subagent-report-semantics' into feat/subagent-settlement-delivery 2026-08-11 13:02:22 +08:00
Yichen Jiang
cc1cf12cb6 Merge remote-tracking branch 'origin/master' into worktree/preset-plane-fallout-p1
Generated docs (`module-graph`, `event-producer-consumer`) taken from master
and regenerated. The `cordis-inspect-jsdoc` golden likewise: master's copy is
the base, and this branch's `presentAs` per-scope rewording is re-applied on
top, since `cordis_inspect` renders that JSDoc into model-visible output.

Hook bypassed as before: the staged-pairing check hands an archived note path
to `verify-translation-pairing`. The full-corpus gate passes.
2026-08-11 12:57:58 +08:00
Hypatia May
85dd22fd4f feat(subagent): deliver continuable child settlement to parents
A continuable child that stopped without reporting — an error, a token
ceiling, cancellation, teardown — left its parent nothing to act on.
The continuation manager now delivers an unconditional settlement
notice to the durable direct parent before releasing ownership, folding
consumed work (foldConsumedWork supersedes findLastMessageTurnEnd) so a
claimed-but-unrun prompt reads as aborted rather than completed, waking
an idle parent, steering a busy one, and never waking a closing tree.
2026-08-11 12:31:49 +08:00
creatixchu
2a755f2863 Merge remote-tracking branch 'origin/master' into feat/read-image-context 2026-08-11 11:54:22 +08:00
Yichen Jiang
aa6abf218c Merge remote-tracking branch 'origin/master' into worktree/web-plugin-config 2026-08-11 11:40:38 +08:00
creatixchu
9186824e87 feat(session): refuse session logs a build cannot faithfully read
Old runtimes meeting a newer session format now fail loud instead of
misreading: version refusal names the direction (newer: upgrade the
harness; older: no upgrade path) and points at the raw JSONL log, and an
event type outside the generated known vocabulary refuses resume unless
its envelope carries the new ignorable: true marker (default: required,
so a forgotten marker over-refuses instead of silently resuming a gutted
session). gen-persistence-catalog now also emits
KNOWN_SESSION_EVENT_TYPES; SQLite stores the marker in a dedicated
column (SCHEMA_VERSION 15). The versioning design (monotonic integer,
n->n+1 upgrader chain, migrate-on-continue) is recorded in the
session-log-version-mechanism Agent Note.
2026-08-11 11:23:48 +08:00
Yichen Jiang
fdd64e9283 Merge origin/master into worktree/web-plugin-config
Master moved every workspace edge to workspace:^ and added release-member
fields; this branch's manifests follow, keeping only the dependency edges it
contributes. The client-runtime README keeps this branch's paragraph: master
did not touch it, and the base/user layers and `unset` it describes are what
this branch added.
2026-08-11 11:16:29 +08:00
Yichen Jiang
5c081a0094 Merge remote-tracking branch 'origin/master' into worktree/preset-plane-fallout-p1
Master moved peerDependencies to `workspace:^`; this branch's two added peers
(`dsh-agent`, `dsh-system-prompt`) take the same form. `docs/module-graph.*`
is generated; regenerated after the merge.

Hook bypassed for the same reason as the previous merge: the staged-pairing
check hands an archived note path to `verify-translation-pairing`. The
full-corpus gate passes.
2026-08-11 11:01:12 +08:00
creatixchu
c1f0a6a683 Merge remote-tracking branch 'origin/master' into feat/read-image-context
# Conflicts:
#	apps/cli/tests/web-agent-presets.e2e.ts
#	packages/fs/tool-fs/package.json
2026-08-11 10:12:14 +08:00
imccyu
b64c3ac1ba release(dsh): 0.0.1-rc.1 2026-08-11 03:20:36 +08:00
Yichen Jiang
19ea7ae573 Merge remote-tracking branch 'origin/master' into worktree/preset-plane-fallout-p1
The pre-commit staged-pairing hook was bypassed for this merge: master's
`docs(notes): archive superseded dsh run decision` (7ee9e16001) arrives as a
rename into `.agents/notes/archived/`, and the hook hands that path to
`verify-translation-pairing`, which correctly refuses an archived note as
out-of-corpus. The full-corpus gate passes (851 pairs).
2026-08-11 00:32:25 +08:00
imccyu
2c85c484d3 build(release): reference workspace members through the workspace protocol
1504 hand-written ranges pointing at workspace members become workspace:^, so
pnpm pack substitutes each member's real version at publication: sibling
peerDependencies follow the family version instead of being pinned at ^0.0.1,
and a reference to a vendored package follows that package's own line. Without
this, publishing 0.0.2 ships peer ranges naming a version that does not exist,
and 0.0.1-rc.1 does not satisfy ^0.0.1 either.

It also retires ranges that had gone stale against the workspace: ^4.0.0-rc.6
for a 4.0.0-rc.7 checkout, ^3.17.0 for schemastery 3.18.0.

workspace:* stays where an exact published version is the point, which is how
the Landlock entry pins its platform packages.

A workspace constraint now requires the protocol, so a new package cannot
reintroduce a hand-written range. The same constraint caught packages/boot/cmdline
arriving on master without the publishable trio, which this change completes.
2026-08-11 00:17:09 +08:00
imccyu
97eb14a007 build(release): make the release set publishable under the private scope
Every package under packages/, apps/, and vendor/ drops "private": true and
declares publishConfig.access "restricted": the repository now states which
packages it publishes instead of deciding it at publish time. Each one also
declares its repository and directory, which is how a consumer of a private
package reaches its source.

The Landlock packages move to restricted with them. They have never been
published, so nothing anonymous depends on them today, and the whole
@deepseek-ai scope stays private.

The workspace constraint that required every package to be private now applies
to non-members only, and asserts the publishable trio on each release member.
2026-08-11 00:09:31 +08:00
Yichen Jiang
1c158ec72b Merge origin/master into worktree/web-plugin-config
The web-app bundle gained dsh-app-boot on master beside this branch's
dependency list; both rows stand, and verify-cordis-config confirms every
patch row still resolves from that manifest.
2026-08-11 00:07:30 +08:00
Yichen Jiang
a7eab2867a Merge remote-tracking branch 'origin/master' into worktree/preset-plane-fallout-p1
`minimal` was rewritten upstream into a fixed-prompt PTY surface that now
carries its own compaction group, so this branch's token-meter move applies to
it too: the row leaves the group and `tokenMeter` leaves the realm, exactly as
in the other three presets. Master's header prose is kept whole — the note this
branch had added there described a composition that no longer exists.

`docs/event-producer-consumer.*` is generated; regenerated after the merge.
2026-08-10 23:50:28 +08:00
Turtle
b374c16fac test(agent-loop): wait for asynchronous reload startup 2026-08-10 23:45:05 +08:00
Turtle
d4ccfbd80f refactor(cli)!: complete app-owned profile startup 2026-08-10 23:45:04 +08:00
Yichen Jiang
0b42259b82 Merge origin/master into worktree/web-plugin-config
Resolves the vendored-package rescope (cordis -> @deepseek-ai/cordis,
schemastery -> @deepseek-ai/schemastery) against this branch's settings
namespaces: the bash capability namespace, its two executors' section
installs, and the new plugin-config client package all move to the scoped
specifiers.
2026-08-10 23:13:11 +08:00
Yichen Jiang
fe221be572 Merge remote-tracking branch 'origin/master' into worktree/preset-plane-fallout-p1
The vendored Cordis rescope (`cordis` -> `@deepseek-ai/cordis`,
`@cordisjs/plugin-*` -> `@deepseek-ai/cordis-plugin-*`) collided with this
branch's two added edges. Resolved by taking master's package names and
keeping this branch's additions: `@deepseek-ai/dsh-agent` and
`@deepseek-ai/dsh-system-prompt` peers, the `scopeChainOf` import, and the
`agent/created` type-only edge.

`docs/event-producer-consumer.*` is generated; regenerated after the merge
rather than hand-resolved.
2026-08-10 23:00:23 +08:00
Yichen Jiang
1cfbafab6a fix(preset): keep the token meter host-plane and name unjoined agents
Moving the agent plane behind presets left two readers on the wrong side of
the host/agent line.

`dsh-token-meter` was disabled on the host and mounted inside each preset's
`compaction` realm, but its three projection units register into the
process-wide `sessionProjections` table. A unit registered from one preset
answers for every session, so whether a `minimal` session showed a context
meter depended on whether some other session had mounted `standard` since
boot, and a process that only ever ran `minimal` showed none. The meter takes
no configuration, keys every fold by Session, and registers no tool or prompt
section, so it returns to the host composition and leaves the presets'
`isolate` map; the realm and `compact-basic` stay, because what a preset
chooses is whether its agent compacts, not whether its tokens are counted.

Nothing named an agent that joined no preset. The join is a scope-parent link,
and without it the tools, prompt-section, and skill views resolve the empty
global layer: the agent publishes, the turn runs, and the model receives
nothing. `AgentPresets` now logs one warning per such agent while a roster is
configured, and the invariant companion fails outright — at
`system-prompt/assemble` rather than at publication, because an unjoined agent
is legal until it addresses a model and `recompose` binds exactly such an
agent. The warning stays advisory: a synchronous `agent/created` throw vetoes
publication, and the ACP bridge, SDK server, and headless bundle all create an
unjoined agent today.

Three limits are recorded rather than fixed: projection key presence is not a
per-session capability signal, a superseded standing generation is never
reclaimed, and a `cordis_mount` temporary plugin belongs to the composition
rather than the session that mounted it.

Fixes #2203
2026-08-10 22:36:06 +08:00
Yichen Jiang
b87a3b1baf Merge remote-tracking branch 'origin/master' into worktree/fix-minimal-preset-prompt 2026-08-10 22:18:22 +08:00
imccyu
ec601ca13d build(vendor): rescope the vendored Cordis packages into @deepseek-ai
Machine-produced by `pnpm run rescope-vendor --apply` plus the regeneration it
prints: `pnpm install` for the lockfile, `pnpm run gen-third-party-notices`,
`verify-translation-pairing --write` for the touched bilingual pairs,
`gen-doc-graphs`, and one typert snapshot whose ids embed character offsets.
`pnpm run rescope-vendor --check` verifies the result.

Renames nine vendored packages (cordis, cosmokit, schemastery and the six
@cordisjs plugins) and every reference that resolves them: manifest names and
dependency keys, module specifiers including declare-module merges, cordis.yml
plugin names, tsconfig paths, every Markdown fence, and `docs/` prose.
Directory names, upstream versions, and dependency ranges are unchanged, so
vendor/README.md still reads as an upstream snapshot; its manifest table gains
an upstream-name column so THIRD_PARTY_NOTICES keeps MIT attribution pointed
at each fork's origin.

The tutorial tier follows the rename end to end: its yaml fences named plugins
the Loader can no longer resolve, its `ts ignore-check` fences disagreed with
the compiled fences beside them, and its prose quoted both. The contracts that
told readers to keep upstream names — the root convention and the vendoring
cookbook's tree comment and manifest invariant — now say to rescope instead.

Two rules read `@deepseek-ai/` as "another workspace plugin": the client bundle
purity gate now names the vendored libraries a browser bundle inlines, and the
files where a bare `cordis` is an agent-preset id keep that product data.
2026-08-10 22:04:13 +08:00